Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Summary/Objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.49
    ৫
    1.31
    િ
    1.29
    and
    1.28
    ़
    1.26
    lessons
    1.24
     couv
    1.23
     strollers
    1.21
    agé
    1.20
    Translatef
    1.20
    POSITIVE LOGITS
     PST
    1.24
    ない
    1.19
    主義
    1.19
    tır
    1.18
     뿌
    1.17
    eran
    1.16
     renowned
    1.15
    ive
    1.15
    পির
    1.13
    er
    1.12
    Act Density 0.002%

    No Known Activations